The notification chimed on Maya's phone – “Liam_the_Llama sent you a friend request.” She nearly dropped her smoothie. Liam, her online confidant for the past year, the witty voice behind the screen, the keeper of secrets shared over late-night Discord calls, wanted to be *friends* friends. A giggle escaped her as she accepted. She’d been meticulously crafting the perfect Instagram profile, the very essence of *cool girl vibes*, in preparation for this moment.

She messaged him immediately, "Hey! Fancy seeing you here!" Her thumbs flew across the screen, a flurry of excitement. She felt a warmth bloom in her chest, a lightness that made her bounce on the balls of her feet. This was it – the culmination of months of carefully curated online interactions.

Later that week, strolling through the farmers market, she spotted a familiar face – Liam, laughing with someone. His online persona was now a real person, in her city, within reach. She sauntered over, a confident smile plastered on her face, and smoothly inserted herself into their conversation, her voice a pitch higher than usual.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion proud. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 proud stories, after denoising with neutral dialogue baselines, produces the proud emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the proud vector is projected through the unembedding matrix.

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453